netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Taehee Yoo <ap420073@gmail.com>
To: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: David Miller <davem@davemloft.net>, Netdev <netdev@vger.kernel.org>
Subject: Re: [PATCH net] vxlan: do not destroy fdb if register_netdevice() is failed
Date: Wed, 26 Jun 2019 01:08:47 +0900	[thread overview]
Message-ID: <CAMArcTWG-KLsmzrtQRGGmnUN31yz4UMqJ9FLyv3xNNPoXY_6=Q@mail.gmail.com> (raw)
In-Reply-To: <CAJieiUjri=-w2PqB9q5fEa=4jqkTWSfK0dUwnT7Cvxdo2sRRzg@mail.gmail.com>

On Tue, 25 Jun 2019 at 13:12, Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
>

Hi Roopa,

Thank you for the review!

> On Sun, Jun 23, 2019 at 7:18 PM Taehee Yoo <ap420073@gmail.com> wrote:
> >
> > On Mon, 24 Jun 2019 at 03:07, David Miller <davem@davemloft.net> wrote:
> > >
> >
> > Hi David,
> >
> > Thank you for the review!
> >
> > > From: Taehee Yoo <ap420073@gmail.com>
> > > Date: Thu, 20 Jun 2019 20:51:08 +0900
> > >
> > > > __vxlan_dev_create() destroys FDB using specific pointer which indicates
> > > > a fdb when error occurs.
> > > > But that pointer should not be used when register_netdevice() fails because
> > > > register_netdevice() internally destroys fdb when error occurs.
> > > >
> > > > In order to avoid un-registered dev's notification, fdb destroying routine
> > > > checks dev's register status before notification.
> > >
> > > Simply pass do_notify as false in this failure code path of __vxlan_dev_create(),
> > > thank you.
> >
> > Failure path of __vxlan_dev_create() can't handle do_notify in that case
> > because if register_netdevice() fails it internally calls
> > ->ndo_uninit() which is
> > vxlan_uninit().
> > vxlan_uninit() internally calls vxlan_fdb_delete_default() and it callls
> > vxlan_fdb_destroy().
> > do_notify of vxlan_fdb_destroy() in vxlan_fdb_delete_default() is always true.
> > So, failure path of __vxlan_dev_create() doesn't have any opportunity to
> > handle do_notify.
>
>
> I don't see register_netdevice calling ndo_uninit in case of all
> errors. In the case where it does not,
> does your patch leak the fdb entry ?.
>
> Wondering if we should just use vxlan_fdb_delete_default with a notify
> flag to delete the entry if exists.
> Will that help ?
>
> There is another commit that touched this code path:
> commit 6db9246871394b3a136cd52001a0763676563840
>
> Author: Petr Machata <petrm@mellanox.com>
> Date:   Tue Dec 18 13:16:00 2018 +0000
>     vxlan: Fix error path in __vxlan_dev_create()

I have checked up failure path of register_netdevice().
Yes, this patch leaks fdb entry.
There are 3 failure cases in the register_netdevice().
A. error occurs before calling ->ndo_init().
it doesn't call ->ndo_uninit().
B. error occurs after calling ->ndo_init().
it calls ->ndo_uninit() and dev->reg_state is NETREG_UNINITIALIZED.
C. error occurs after registering netdev. it calls rollback_registered().
rollback_registered() internally calls ->ndo_uninit()
and dev->reg_state is NETREG_UNREGISTERING.

A panic due to these problem could be fixed by using
vxlan_fdb_delete_default() with notify flag.
But notification problem could not be fixed clearly
because of the case C.

I don't have clear solution for the case C.
Please let me know, if you have any good idea for fixing the case C.

Thank you!

  reply	other threads:[~2019-06-25 16:09 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-20 11:51 [PATCH net] vxlan: do not destroy fdb if register_netdevice() is failed Taehee Yoo
2019-06-23 18:07 ` David Miller
2019-06-24  2:18   ` Taehee Yoo
2019-06-25  4:12     ` Roopa Prabhu
2019-06-25 16:08       ` Taehee Yoo [this message]
2019-06-26  5:03         ` Roopa Prabhu
2019-06-26 14:53           ` Taehee Yoo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAMArcTWG-KLsmzrtQRGGmnUN31yz4UMqJ9FLyv3xNNPoXY_6=Q@mail.gmail.com' \
    --to=ap420073@gmail.com \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=roopa@cumulusnetworks.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).